activity
20172025
most citedGraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation

210 citations · 671 across the 21 of their papers we have counts for

collaborators

23 papers

cs.LG2025

Overcoming Long-Context Limitations of State-Space Models via Context-Dependent Sparse Attention

Zhihao Zhan, Jianan Zhao, Zhaocheng Zhu +1

Efficient long-context modeling remains a critical challenge for natural language processing (NLP), as the time complexity of the predominant Transformer architecture scales quadra…

cs.LG2025

From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?

Zhanke Zhou, Xiao Feng, Zhaocheng Zhu +3

While existing benchmarks probe the reasoning abilities of large language models (LLMs) across diverse domains, they predominantly assess passive reasoning, providing models with a…

cs.LG2025

Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models

Zhanke Zhou, Zhaocheng Zhu, Xuan Li +5

Numerous applications of large language models (LLMs) rely on their ability to perform step-by-step reasoning. However, the reasoning behavior of LLMs remains poorly understood, po…

cs.AI2024

Learning Representations for Reasoning: Generalizing Across Diverse Structures

Zhaocheng Zhu

Reasoning, the ability to logically draw conclusions from existing knowledge, is a hallmark of human. Together with perception, they constitute the two major themes of artificial i…

cs.LG2024★ 1 cited

Fully-inductive Node Classification on Arbitrary Graphs

Jianan Zhao, Zhaocheng Zhu, Mikhail Galkin +3

One fundamental challenge in graph machine learning is generalizing to new graphs. Many existing methods following the inductive setup can generalize to test graphs with new struct…

cs.AI2024

A Foundation Model for Zero-shot Logical Query Reasoning

Mikhail Galkin, Jincheng Zhou, Bruno Ribeiro +2

Complex logical query answering (CLQA) in knowledge graphs (KGs) goes beyond simple KG completion and aims at answering compositional queries comprised of multiple projections and…

cs.LG2023

Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets

Dominique Beaini, Shenyang Huang, Joao Alex Cunha +32

Recently, pre-trained foundation models have enabled significant advancements in multiple fields. In molecular machine learning, however, where datasets are often hand-curated, and…

cs.CL2023★ 4 cited

GraphText: Graph Reasoning in Text Space

Jianan Zhao, Le Zhuo, Yikang Shen +5

Large Language Models (LLMs) have gained the ability to assimilate human knowledge and facilitate natural language interactions with both humans and other LLMs. However, despite th…

cs.AI2023★ 8 cited

Large Language Models can Learn Rules

Zhaocheng Zhu, Yuan Xue, Xinyun Chen +4

When prompted with a few examples and intermediate steps, large language models (LLMs) have demonstrated impressive performance in various reasoning tasks. However, prompting metho…

cs.CL2023★ 9 cited

Towards Foundation Models for Knowledge Graph Reasoning

Mikhail Galkin, Xinyu Yuan, Hesham Mostafa +2

Foundation models in language and vision have the ability to run inference on any textual and visual inputs thanks to the transferable representations such as a vocabulary of token…

cs.DB2023★ 9 cited

Neural Graph Reasoning: Complex Logical Query Answering Meets Graph Databases

Hongyu Ren, Mikhail Galkin, Michael Cochez +2

Complex logical query answering (CLQA) is a recently emerged task of graph machine learning that goes beyond simple one-hop link prediction and solves a far more complex task of mu…

cs.AI2022★ 4 cited

Inductive Logical Query Answering in Knowledge Graphs

Mikhail Galkin, Zhaocheng Zhu, Hongyu Ren +1

Formulating and answering logical queries is a standard communication interface for knowledge graphs (KGs). Alleviating the notorious incompleteness of real-world KGs, neural metho…

cs.AI2022★ 10 cited

A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphs

Zhaocheng Zhu, Xinyu Yuan, Mikhail Galkin +4

Reasoning on large-scale knowledge graphs has been long dominated by embedding methods. While path-based methods possess the inductive capacity that embeddings lack, their scalabil…

cs.LG2022★ 59 cited

PEER: A Comprehensive and Multi-Task Benchmark for Protein Sequence Understanding

Minghao Xu, Zuobai Zhang, Jiarui Lu +5

We are now witnessing significant progress of deep learning methods in a variety of tasks (or datasets) of proteins. However, there is a lack of a standard benchmark to evaluate th…

cs.AI2022★ 16 cited

Neural-Symbolic Models for Logical Queries on Knowledge Graphs

Zhaocheng Zhu, Mikhail Galkin, Zuobai Zhang +1

Answering complex first-order logic (FOL) queries on knowledge graphs is a fundamental task for multi-hop reasoning. Traditional symbolic methods traverse a complete knowledge grap…

cs.LG2022★ 32 cited

TorchDrug: A Powerful and Flexible Machine Learning Platform for Drug Discovery

Zhaocheng Zhu, Chence Shi, Zuobai Zhang +12

Machine learning has huge potential to revolutionize the field of drug discovery and is attracting increasing attention in recent years. However, lacking domain knowledge (e.g., wh…

cs.LG2021★ 114 cited

Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction

Zhaocheng Zhu, Zuobai Zhang, Louis-Pascal Xhonneux +1

Link prediction is a very fundamental task on graphs. Inspired by traditional path-based methods, in this paper we propose a general and flexible representation learning framework…

cs.LG2020★ 210 cited

GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation

Chence Shi, Minkai Xu, Zhaocheng Zhu +3

Molecular graph generation is a fundamental problem for drug discovery and has been attracting growing attention. The problem is challenging since it requires not only generating c…

cs.CL2019★ 80 cited

KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation

Xiaozhi Wang, Tianyu Gao, Zhaocheng Zhu +4

Pre-trained language representation models (PLMs) cannot well capture factual knowledge from text. In contrast, knowledge embedding (KE) methods can effectively represent the relat…

cs.LG2019

Self-Adaptive Network Pruning

Jinting Chen, Zhaocheng Zhu, Cheng Li +1

Deep convolutional neural networks have been proved successful on a wide range of tasks, yet they are still hindered by their large computation cost in many industrial scenarios. I…

cs.LG2019★ 108 cited

GraphVite: A High-Performance CPU-GPU Hybrid System for Node Embedding

Zhaocheng Zhu, Shizhen Xu, Meng Qu +1

Learning continuous representations of nodes is attracting growing interest in both academia and industry recently, due to their simplicity and effectiveness in a variety of applic…

cs.CV2018

Saliency Supervision: An Intuitive and Effective Approach for Pain Intensity Regression

Conghui Li, Zhaocheng Zhu, Yuming Zhao

Getting pain intensity from face images is an important problem in autonomous nursing systems. However, due to the limitation in data sources and the subjectiveness in pain intensi…

cs.CL2017★ 7 cited

Context Aware Document Embedding

Zhaocheng Zhu, Junfeng Hu

Recently, doc2vec has achieved excellent results in different tasks. In this paper, we present a context aware variant of doc2vec. We introduce a novel weight estimating mechanism…